Skip to content
SDB

AI Tutorials

ML Fundamentals

Master the full spectrum of machine learning — supervised, unsupervised, reinforcement, ensembles, deep networks, CNNs, RNNs, evaluation metrics, hyperparameter tuning, AutoML, and recommendation systems with hands-on code.

16 chapters · 521 min

← All AI tutorials

Core machine learning algorithms and techniques from first principles

  1. Ch. 01

    Supervised Learning

    The complete taxonomy — regression, classification, time series, and probabilistic models

    beginner · 45 min

    Read →
  2. Ch. 02

    Unsupervised Learning

    Clustering, dimensionality reduction, and density estimation on unlabeled data

    beginner · 28 min

    Read →
  3. Ch. 03

    Reinforcement Learning

    Agents, environments, rewards, and the algorithms that learn through trial and error

    intermediate · 28 min

    Read →
  4. Ch. 04

    Semi-Supervised & Self-Supervised Learning

    Learning from limited labels and from data structure itself

    intermediate · 22 min

    Read →
  5. Ch. 05

    Ensemble Techniques

    Bagging, boosting, stacking, and why combining models beats any single learner

    intermediate · 32 min

    Read →
  6. Ch. 06

    Deep Neural Networks

    Perceptrons, backpropagation, activation functions, and training deep networks

    intermediate · 30 min

    Read →
  7. Ch. 07

    Convolutional Neural Networks (CNNs)

    Spatial feature extraction, pooling, and the architectures behind modern computer vision

    intermediate · 28 min

    Read →
  8. Ch. 08

    RNN, LSTM & GRU

    Recurrent architectures for sequential data: text, time series, and speech

    intermediate · 28 min

    Read →
  9. Ch. 09

    Model Evaluation Metrics & Techniques

    Classification, regression, clustering, and ranking metrics — plus cross-validation techniques

    beginner · 38 min

    Read →
  10. Ch. 10

    Important Hyperparameters

    A systematic guide to tuning learning rate, regularization, architecture, and search strategies

    intermediate · 25 min

    Read →
  11. Ch. 11

    EDA & AutoML

    Exploratory Data Analysis, feature engineering, dimensionality reduction, and AutoML

    beginner · 36 min

    Read →
  12. Ch. 12

    Recommendation Systems

    Collaborative filtering, matrix factorization, content-based, and deep learning approaches

    intermediate · 30 min

    Read →
  13. Ch. 13

    Time Series Forecasting

    ARIMA, Prophet, and Temporal Fusion Transformer for demand forecasting and anomaly detection

    intermediate · 35 min

    Read →
  14. Ch. 14

    Graph Neural Networks (GNNs)

    GCN, GraphSAGE, and GAT — deep learning on graph-structured data for fraud detection, drug discovery, and recommendations

    advanced · 38 min

    Read →
  15. Ch. 15

    Causal Inference

    Counterfactuals, do-calculus, A/B testing, and propensity scoring for data-driven decision making

    advanced · 40 min

    Read →
  16. Ch. 16

    Bayesian Machine Learning

    Gaussian Processes, Bayesian optimization, and prior/posterior reasoning for uncertainty quantification

    advanced · 38 min

    Read →